mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
128 lines
5.1 KiB
Python
128 lines
5.1 KiB
Python
"""Tests for voice mode platform isolation (bug #12542).
|
|
|
|
Voice mode state stored as {chat_id: mode} without a platform namespace
|
|
caused collisions: Telegram chat '123' and Slack chat '123' shared the
|
|
same key. The fix prefixes keys with platform value: 'telegram:123' vs
|
|
'slack:123'.
|
|
"""
|
|
|
|
import json
|
|
import tempfile
|
|
from pathlib import Path
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
|
|
from gateway.config import Platform
|
|
from gateway.run import GatewayRunner
|
|
|
|
|
|
class TestVoiceKeyHelper:
|
|
"""Test the _voice_key helper method."""
|
|
|
|
|
|
def test_voice_key_different_platforms_same_chat_id(self):
|
|
"""Same chat_id on different platforms yields different keys."""
|
|
runner = _make_runner()
|
|
key_telegram = runner._voice_key(Platform.TELEGRAM, "123")
|
|
key_slack = runner._voice_key(Platform.SLACK, "123")
|
|
key_discord = runner._voice_key(Platform.DISCORD, "123")
|
|
assert key_telegram != key_slack
|
|
assert key_slack != key_discord
|
|
assert key_telegram == "telegram:123"
|
|
assert key_slack == "slack:123"
|
|
assert key_discord == "discord:123"
|
|
|
|
|
|
class TestVoiceModePlatformIsolation:
|
|
"""Test that voice mode state is isolated by platform."""
|
|
|
|
def test_telegram_and_slack_voice_mode_independent(self):
|
|
"""Setting voice mode for Telegram chat '123' does not affect Slack chat '123'."""
|
|
runner = _make_runner()
|
|
|
|
# Enable voice mode for Telegram chat '123'
|
|
runner._voice_mode[runner._voice_key(Platform.TELEGRAM, "123")] = "all"
|
|
# Enable voice mode for Slack chat '123' to a different mode
|
|
runner._voice_mode[runner._voice_key(Platform.SLACK, "123")] = "voice_only"
|
|
|
|
# Verify they are independent
|
|
assert runner._voice_mode.get(runner._voice_key(Platform.TELEGRAM, "123")) == "all"
|
|
assert runner._voice_mode.get(runner._voice_key(Platform.SLACK, "123")) == "voice_only"
|
|
|
|
# Disabling Telegram should not affect Slack
|
|
runner._voice_mode[runner._voice_key(Platform.TELEGRAM, "123")] = "off"
|
|
assert runner._voice_mode.get(runner._voice_key(Platform.TELEGRAM, "123")) == "off"
|
|
assert runner._voice_mode.get(runner._voice_key(Platform.SLACK, "123")) == "voice_only"
|
|
|
|
|
|
class TestLegacyKeyMigration:
|
|
"""Test migration of legacy unprefixed keys in _load_voice_modes."""
|
|
|
|
def test_load_voice_modes_skips_legacy_keys(self):
|
|
"""_load_voice_modes skips keys without ':' prefix and logs a warning."""
|
|
runner = _make_runner()
|
|
|
|
# Simulate legacy persisted data with unprefixed keys
|
|
legacy_data = {
|
|
"123": "all",
|
|
"456": "voice_only",
|
|
# Also includes a properly prefixed key (from after the fix)
|
|
"telegram:789": "off",
|
|
}
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
voice_path = Path(tmpdir) / "gateway_voice_mode.json"
|
|
voice_path.write_text(json.dumps(legacy_data))
|
|
|
|
with patch.object(runner, "_VOICE_MODE_PATH", voice_path):
|
|
with patch("gateway.run.logger") as mock_logger:
|
|
result = runner._load_voice_modes()
|
|
|
|
# Legacy keys without ':' should be skipped
|
|
assert "123" not in result
|
|
assert "456" not in result
|
|
# Prefixed key should be preserved
|
|
assert result.get("telegram:789") == "off"
|
|
# Warning should be logged for each legacy key
|
|
assert mock_logger.warning.called
|
|
warning_calls = [str(call) for call in mock_logger.warning.call_args_list]
|
|
assert any("Skipping legacy unprefixed voice mode key" in str(c) for c in warning_calls)
|
|
|
|
|
|
class TestSyncVoiceModeStateToAdapter:
|
|
"""Test _sync_voice_mode_state_to_adapter filters by platform."""
|
|
|
|
def test_sync_only_includes_platform_chats(self):
|
|
"""Only chats matching the adapter's platform are synced."""
|
|
runner = _make_runner()
|
|
|
|
# Set up voice mode state with multiple platforms
|
|
runner._voice_mode = {
|
|
"telegram:123": "off", # Should sync
|
|
"telegram:456": "all", # Should NOT sync (mode is not "off")
|
|
"slack:123": "off", # Should NOT sync (different platform)
|
|
"discord:789": "off", # Should NOT sync (different platform)
|
|
}
|
|
|
|
# Create a mock Telegram adapter
|
|
mock_adapter = MagicMock()
|
|
mock_adapter.platform = Platform.TELEGRAM
|
|
mock_adapter._auto_tts_disabled_chats = set()
|
|
|
|
runner._sync_voice_mode_state_to_adapter(mock_adapter)
|
|
|
|
# Only telegram:123 should be in disabled_chats (mode="off" for telegram)
|
|
assert mock_adapter._auto_tts_disabled_chats == {"123"}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Helper
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _make_runner() -> GatewayRunner:
|
|
"""Create a minimal GatewayRunner for testing."""
|
|
with patch("gateway.run.GatewayRunner._load_voice_modes", return_value={}):
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
runner._voice_mode = {}
|
|
runner.adapters = {}
|
|
return runner
|